QQWorld: 分位数-分位数マッチングによる世界モデル正則化
QQWorld: Quantile-Quantile Matching for World Model Regularization
潜在世界モデルの正則化に用いられるEpps-Pulley目的関数が裾野で勾配消失する問題を指摘し、分位数-分位数マッチングに置き換えたQQWorldを提案。さらに過去バッチのサンプルを利用するクロスバッチQQでランキングプールを拡大し、制御環境で計画成功率と潜在分布のガウス性を改善した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Zhoushun Yu, Xiaoyu Hu, Xiangyu Xu
分類: cs.LG, cs.AI, cs.CV, cs.MM, cs.RO
原文アブストラクト
Latent world models enable efficient planning by predicting future states in a compact representation space, but their performance depends critically on the quality of the learned latent distribution. LeWorldModel (LeWM) regularizes its latents toward an isotropic Gaussian using the Epps-Pulley (EP) objective. We show that the corrective gradients of EP rapidly vanish for isolated tail samples, leaving heavy-tailed deviations insufficiently controlled. To address this limitation, we propose QQWorld, which replaces EP with a quantile-quantile matching objective that directly aligns projected latent samples with rank-matched Gaussian quantiles, thereby maintaining effective corrective gradients in the tails. We further develop cross-batch QQ, which enlarges the effective ranking pool using detached samples from previous batches, and characterize its bias-variance trade-off. Across four control environments, QQWorld effectively improves the average planning success rate of LeWM, while consistently yielding better Gaussian alignment and thinner latent tails.
